LongCounsel-8 is a benchmark suite comprising three independently generated datasets with 7,749 five‑session counseling trajectories, designed to evaluate longitudinal depression tracking. The datasets are grounded in real‑world client profiles, depression trajectories, symptom compositions, and counseling patterns, and they address challenges of longitudinal consistency, empirical grounding, and natural expression of controlled depression states. Experiments show that lower single‑session error does not guarantee accurate trend identification, that methods perform worse on worsening trajectories, and that adding more session history can reduce trend prediction accuracy.
arXiv:2605.22286v2 Announce Type: replace-cross
Abstract: Text-based counseling provides a valuable source of information for assessing depression severity. We study prediction of the total score on...
By Zhaomin Wu, Jiayi Li, Bingsheng He
The study investigates how a large language model, Gemma-3-27B-PT, internally represents depressive symptoms. By applying mechanistic interpretability methods to the model’s residual stream, researchers found that symptom groups are geometrically distinct at layer 21, and that projected symptom vectors align with clinician-annotated rankings across mood, somatic, and suicidality dimensions. Additionally, a single depression vector at this layer can differentiate depressive from non-depressive text with an AUC of 0.789, suggesting a potential emotional valence gate for symptom projection.
By Fangyi Zhu, Ajay Subramanian, Allison Constant, Camille Wang, Ravish Gupta, Corey J. Keller
arXiv:2607. 27224v1 Announce Type: cross Abstract: External and synthetic control arms (ECAs) are entering psychiatric drug development, but the field lacks a benchmark that evaluates the properties regulators care about: not only how accurately a method reconstructs untreated trajectories, but whether its uncertainty is calibrated, whether it is robust to the informative observation times common in mental-health records (sicker patients are seen more often), and what false-positive rate it induces in go/no-go trial decisions.
By Aakash Bhagat, Shashank Choudhary
arXiv:2607. 15202v1 Announce Type: new Abstract: Annotation quality is a major bottleneck in building reliable and explainable artificial intelligence (XAI) systems for mental health research.
By Hoang-Loc Cao, Van Pham, Truong Thanh Hung Nguyen, Phuc Truong Loc Nguyen, Phuc Ho, Veronica Whitford, Hung Cao
BALMS is a benchmark for evaluating large language model (LLM) agents that analyze longitudinal wearable data to predict mental‑health wellbeing scores and generate evidence‑grounded rationales. It covers three real‑world datasets, two task families (score prediction and rationale generation), and tests five LLM backbones across open‑ and closed‑source paradigms. The study finds that zero‑shot agents rarely beat a simple mean baseline, and while chain‑of‑thought prompting helps reasoning, it does not ensure temporal grounding or numerical accuracy.
By Yu Yvonne Wu, Arvind Pillai, Yuliang Chen, Yuwei Zhang, Sudarshan Regmi, Tess Z. Griffin, Michael V. Heinz, Lisa A. Marsch, Nicholas C. Jacobson, Andrew Campbell